Related papers: How Coding Agents Fail Their Users: A Large-Scale …
Despite the increasing presence of AI assistants in Integrated Development Environments (IDEs), it remains unclear what different groups of developers actually need from these tools and which features are likely to be implemented in…
A rapidly growing body of research is examining how LLMs influence developers when they code. To date, this research has tended to focus on productivity and code quality outcomes, rather than the underlying cognitive processes involved in…
As autonomous coding agents see rapid adoption, their evaluation has primarily focused on task completion rates holding the target codebase fixed. This leaves a critical question unanswered: does the structural and stylistic quality, or…
AI agents are systems capable of perceiving their environment, autonomously planning and executing tasks. Recent advancements in LLM have introduced a transformative paradigm for AI agents, enabling them to interact with external resources…
Despite coding agents' advances in handling increasingly complex tasks, their continued tendency to introduce unintended edits, subtle bugs, and scope drift that slip past code review means developers must still decide how much autonomy to…
Achieving human-AI alignment in complex multi-agent games is crucial for creating trustworthy AI agents that enhance gameplay. We propose a method to evaluate this alignment using an interpretable task-sets framework, focusing on high-level…
Background: Large language models are typically evaluated as models, benchmarks, or short conversational episodes. Less is known about what happens when an agent is embedded persistently in a real academic research environment with durable…
Coding agents have received significant adoption in software development recently. Unlike traditional LLM-based code completion tools, coding agents work with autonomy (e.g., invoking external tools) and leave visible traces in software…
Coding agents are rapidly changing the landscape of software development, moving from inline completion to autonomous systems that edit repositories, open pull requests, respond to issues, and run scheduled or webhook triggered routines…
As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…
Resolving team conflicts requires not only task-specific competence, but also social intelligence to find common ground and build consensus. As AI agents increasingly collaborate on complex work, they must develop coordination capabilities…
Foundation model (FM)-based AI agents are rapidly gaining adoption across diverse domains, but their inherent non-determinism and non-reproducibility pose testing and quality assurance challenges. While recent benchmarks provide task-level…
AI coding assistants and autonomous agents are becoming integral to software development workflows, reshaping how code is produced, reviewed, and maintained. While recent research has focused mainly on the capabilities and impacts of…
Assistive agents for Blind and Visually Impaired (BVI) users require accessibility alignment as a first-class design objective. Despite rapid progress in agentic AI, most systems are designed and evaluated under assumptions of sighted…
Traditional software relies on contracts -- APIs, type systems, assertions -- to specify and enforce correct behavior. AI agents, by contrast, operate on prompts and natural language instructions with no formal behavioral specification.…
As large language model (LLM) based agents interact autonomously with one another, a new class of failures emerges that cannot be predicted from single agent performance: behavioral drifts in agent-agent conversations (AxA). Unlike…
This position paper states that AI Alignment in Multi-Agent Systems (MAS) should be considered a dynamic and interaction-dependent process that heavily depends on the social environment where agents are deployed, either collaborative,…
Value alignment problems arise in scenarios where the specified objectives of an AI agent don't match the true underlying objective of its users. The problem has been widely argued to be one of the central safety problems in AI.…
Using a sample of 25,000 Bing Copilot conversations, we study how the agent responds to users of varying levels of domain expertise and the resulting impact on user experience along multiple dimensions. Our findings show that across a…
The rapid integration of Large Language Models (LLMs) into software development workflows has given rise to a new class of AI-assisted coding tools, such as Claude-Code, Codex, and Gemini CLIs. While promising significant productivity…